---
schema_version: "1"
id: e1348fbd015c760fa7b96fcbb0375f26265a155c41f4ace331d73ab8aa9fffa5
title: Configure Text Variables
collection: admin
version: current
locale: en-us
portal_url: https://docs.salesforce.com/admin/current/en-us/analytics/264-0-0/bi_edd_story_text.md
canonical_url: https://help.salesforce.com/s/articleView?id=analytics.bi_edd_story_text.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: 0cc6b3baa11aaa86eb6a5a121252c624e507b81b751cf1dd72ca4b06d6414b84
description: Configure settings for individual text variables in your model.
products:
  - CRM Analytics
  - Cross Cloud
release: "264"
---
# Configure Text Variables

Configure settings for individual text variables in your model.

### Required Editions

![Note](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/images/icon_note.png)

Note Einstein Discovery stories are now models. We wish we could snap our fingers to update the name everywhere, but you can expect to see the previous name in a few places until we replace it.

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small edition"><colgroup><col></colgroup><tbody><tr class=""><td class="slds-cell-wrap" style="vertical-align:top;">Available in Salesforce Classic and Lightning Experience.</td></tr><tr class=""><td class="slds-cell-wrap" style="vertical-align:top;">Available with CRM Analytics, which is available for an extra cost in <strong>Enterprise</strong>, <strong>Performance</strong>, and <strong>Unlimited</strong> Editions. Also available in <strong>Developer</strong> Edition.</td></tr></tbody></table>

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small permission">
          <colgroup>
            <col style="width:50%">
            <col style="width:50%">
          </colgroup>
          <thead class="slds-text-title_caps ">
            <tr class="">
              <th scope="colgroup" class="slds-cell-wrap" colspan="2" style="text-align:center;vertical-align:top;" id="d117874e77">User Permissions
                Needed</th>
            </tr>
          </thead>
          <tbody>
            <tr class="">
              <td data-label="User Permissions Needed" class="slds-cell-wrap" style="vertical-align:top;" headers="d117874e77 ">To configure text fields in a model:</td>

              <td class="slds-cell-wrap" style="vertical-align:top;" headers="d117874e77 ">Create
                and Update Einstein Discovery Models</td>

            </tr>
          </tbody>
        </table>

1. On the Model Settings page, click a text variable. The variable panel appears.
    
    ![Alerts tab for a number field](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/bi/images/bi/bi_edd_story_text.png)
2. In the **Alerts** tab, respond to any suggestions regarding data issues for this field, such as high correlation, strongest predictors, or missing values. For more information, see [Handle Quality Alerts](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_quality_alert.htm&release=264.0.0&type=5 "Einstein Discovery displays quality alerts when it detects issues in your training data, your model’s quality metrics, or during cross-validation.").
    
    ![Edit Variable pane, showing the Alerts tab](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/bi/images/bi/bi_edd_story_text_alert.png)
3. In the **Performance** tab, see how well your model works for each value within the selected variable.
    
    Performance is shown as a decimal score, where 1 is perfect accuracy. For example, in the variable Store, Miami has a performance score of 0.99, and Honolulu has a score of 0.79. You can then conclude that the model performs better for the Miami store than the Honolulu store.
    
    ![Performance tab for a number variable](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/bi/images/bi/bi_edd_story_text_performance.png)
    
    1. Optionally, if using a binary classification or regression model, click **Row Count Analysis** to see a detailed comparison of the values by performance and row count.
        
        ![Row Count Analysis chart for a number variable in a binary classification or regression model](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/bi/images/bi/bi_edd_story_text_performance_rowCountAnalysis.png)
    2. Optionally, if using a multiclass classification model, see the performance of each value by outcome.
        
        - To expand a value to see performance by outcome, click ![Actions button](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/resources-global/analytics/images/actions_button.png).
            - To see a graphic comparison of values and outcomes by performance and row count, click **Row Count Analysis**.
                
                - Use the dropdown to select different outcomes (1). The chart updates according to the selected outcome.
                - Toggle between Actual Class and Predicted Class (2). The **Actual Class** groups data based on the observed value. The **Predicted Class** groups data based on the predicted value.
                
                ![Row Count Analysis chart for a number variable in a multiclass model](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/bi/images/bi/bi_edd_story_text_performance_multiclass_rowCountAnalysis.png)
        - To see a graph of performance by value and outcome, click **Detailed Analysis**. The darker the circle, the better the performance. The bigger the circle, the higher the row count.
            
            ![Detailed Analysis chart for a number variable in a multiclass model](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/bi/images/bi/bi_edd_story_text_performance_detailed_analysis.png)
4. In the **Settings** tab, configure the following settings.
    
    ![Edit Variable pane, showing the Settings tab](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/bi/images/bi/bi_edd_story_text_settings.png)
    
    <table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small ">
            <colgroup>
              <col style="width:19.193857965451055%">
              <col style="width:80.80614203454894%">
            </colgroup>
            <thead class="slds-text-title_caps ">
              <tr class="">
                <th scope="col" class="slds-cell-wrap" style="vertical-align:top;" id="d117874e258">Setting</th>
                <th scope="col" class="slds-cell-wrap" style="vertical-align:top;" id="d117874e261">Description</th>
              </tr>
            </thead>
            <tbody>
              <tr class="">
                <td data-label="Setting" class="slds-cell-wrap" style="vertical-align:top;" headers="d117874e258 ">
                  <strong class="uicontrol">Analyze for bias</strong>
                </td>

                <td data-label="Description" class="slds-cell-wrap" style="vertical-align:top;" headers="d117874e261 ">
                  <p>Select this option to exclude a variable from the model so that it does not
                    influence predictions and recommendations. If selected, Einstein Discovery shows
                    a shield icon next to the title of the insight to remind you it’s a sensitive
                    variable. </p>
                  <div style="text-align:left;"><img style="width:100px;" src="https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/bi/images/bi/bi_edd_story_tenure.png" alt="Shield icon for sensitive fields"></div>
                  <p style="margin-bottom:0;">This option allows you to evaluate and assess the variable’s
                    impact in the model. Einstein Discovery still notifies you if it shows a 50% or
                    higher correlation with the model’s outcome variable.</p>
                </td>

              </tr>
              <tr class="">
                <td data-label="Setting" class="slds-cell-wrap" style="vertical-align:top;" headers="d117874e258 ">
                  <strong class="uicontrol">Transform</strong>
                </td>

                <td data-label="Description" class="slds-cell-wrap" style="vertical-align:top;" headers="d117874e261 ">
                  <p>Select the method to transform your text:</p><a name="bi_edd_story_text__ul_n2s_mmj_ftb"><!-- --></a>
                  <ul id="bi_edd_story_text__ul_n2s_mmj_ftb">
                    <li><strong>Fuzzy Matching</strong> to resolve spelling variations. See <a href="https://help.salesforce.com/s/articleView?id=analytics.bi_edd_story_fuzzy_matching.htm&amp;release=264.0.0&amp;type=5" title="Fuzzy matching adds uniformity to spelling variations in variables, resulting in smarter categorizations and better predictions. Einstein Discovery transforms the data at prediction time, enabling you to skip cleansing during data prep.">Apply Fuzzy Matching for Smarter Categorizations</a>.</li>
                    <li><strong>Detect Sentiment</strong> to categorize unstructured data. See <a href="https://help.salesforce.com/s/articleView?id=analytics.bi_edd_story_sentiment.htm&amp;release=264.0.0&amp;type=5" title="Process unstructured data during model creation and categorize sentiment as positive, negative, or neutral.">Detect Sentiment in Unstructured Text</a>.</li>
                    <li><strong>Text Clustering</strong> to bucket unclustered data by keywords. See <a href="https://help.salesforce.com/s/articleView?id=analytics.bi_edd_story_unstructured_data.htm&amp;release=264.0.0&amp;type=5" title="Text clustering reduces unstructured data to its top keywords and enables you to quickly reveal hidden insights and improve decision making.">Use Text Clustering to Analyze Unstructured Data</a>.</li>
                    <li><strong>Replace Missing Values</strong> to fill in missing values. See <a href="https://help.salesforce.com/s/articleView?id=analytics.bi_edd_story_impute_text.htm&amp;release=264.0.0&amp;type=5" title="Einstein Discovery allows you to impute missing text values in your dataset. Enable imputation on a text variable, and Einstein Discovery automatically replaces missing values with data derived from another subset of your data.">Impute Missing Text Values</a>.</li>
                  </ul>
                </td>

              </tr>
              <tr class="">
                <td data-label="Setting" class="slds-cell-wrap" style="vertical-align:top;" headers="d117874e258 ">
                  <strong class="uicontrol">Include Only</strong>
                </td>

                <td data-label="Description" class="slds-cell-wrap" style="vertical-align:top;" headers="d117874e261 ">Select the values you want to include in the model. Depending on the
                  following options, excluded values are either omitted from analysis or merged
                  into the Other category.</td>

              </tr>
              <tr class="">
                <td data-label="Setting" class="slds-cell-wrap" style="vertical-align:top;" headers="d117874e258 ">
                  <strong class="uicontrol">Histogram</strong>
                </td>

                <td data-label="Description" class="slds-cell-wrap" style="vertical-align:top;" headers="d117874e261 ">A bar chart graph shows the number of values that occur across
                  values.</td>

              </tr>
            </tbody>
          </table>
    
    Changes take effect after you create the model.

- **[Apply Fuzzy Matching for Smarter Categorizations](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_story_fuzzy_matching.htm&release=264.0.0&type=5)**  
    Fuzzy matching adds uniformity to spelling variations in variables, resulting in smarter categorizations and better predictions. Einstein Discovery transforms the data at prediction time, enabling you to skip cleansing during data prep.
- **[Detect Sentiment in Unstructured Text](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_story_sentiment.htm&release=264.0.0&type=5)**  
    Process unstructured data during model creation and categorize sentiment as positive, negative, or neutral.
- **[Use Text Clustering to Analyze Unstructured Data](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_story_unstructured_data.htm&release=264.0.0&type=5)**  
    Text clustering reduces unstructured data to its top keywords and enables you to quickly reveal hidden insights and improve decision making.
- **[Impute Missing Text Values](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_story_impute_text.htm&release=264.0.0&type=5)**  
    Einstein Discovery allows you to impute missing text values in your dataset. Enable imputation on a text variable, and Einstein Discovery automatically replaces missing values with data derived from another subset of your data.